© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 24544
    Prev
    Next
    INDEX
    Explanations

    references to the state of Illinois

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    410
    +0.17
    1.0%
    189
    +0.14
    0.8%
    362
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.17
    0.01
    383
    +0.14
    0.01
    410
    +0.11
    0.02
    Negative Logits
     true
    -1.69
    chers
    -1.48
    ables
    -1.46
     palms
    -1.45
    true
    -1.44
    to
    -1.42
    standing
    -1.42
    bringing
    -1.41
    upon
    -1.41
    tern
    -1.37
    POSITIVE LOGITS
    ustration
    2.55
    berg
    1.85
    ustr
    1.83
    iterate
    1.77
    ieux
    1.72
    etti
    1.72
    umin
    1.68
    izumab
    1.68
    lete
    1.63
    inois
    1.62
    Activations Density 0.077%

    No Known Activations